Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55308
    Prev
    Next
    INDEX
    Explanations

    cool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     нач
    -0.08
     ador
    -0.07
     Stephanie
    -0.07
     menc
    -0.07
     Destiny
    -0.07
     Coroutine
    -0.07
     עת
    -0.07
     unclear
    -0.07
     кр
    -0.07
     terg
    -0.07
    POSITIVE LOGITS
    -headed
    0.09
    Stor
    0.08
    下来
    0.08
    ifie
    0.08
     Nied
    0.08
     breeze
    0.08
    house
    0.08
    fox
    0.07
    圈
    0.07
    liness
    0.07
    Activations Density 0.011%

    No Known Activations